← All instances

g6.16xlarge

⚡ 1x GPU • 24.0 GB

Part of the G6 Accelerated Computing family — Hardware accelerators (GPUs, FPGAs) for specialized compute.

Name:gGPU Graphics & ML Inferenceg = GPU Graphics & ML InferencePowered by GPUs (NVIDIA/AMD) for graphics-intensive applications, video encoding, remote workstations, and machine learning inference.66th Generation6 = 6th GenerationAWS 6th generation hardware platform with updated CPU/system architecture.16xlarge16 Extra Large16xlarge = 16 Extra Large64 vCPUs • 256.0 GiB RAM • 1880 GB NVMe SSD • 25 Gigabit Network • 1x NVIDIA L4 (24.0 GB VRAM)
Price (Linux)
$3.3968/ hr
~$2,479.66/mo
Compute
64vCPUs
32 cores • x86_64
Memory
256.0GiB
4.0 GiB / vCPU
Value
$0.0531/ vCPU-hr
$0.0133/GiB-hr
Network
25Gbps
Baseline: 25 Gbps
Storage & EBS
2,500MB/s
Max: 80,000 IOPS

Technical Specifications & Limits

Hardware specs, container thresholds, and system limits

Compute & Processor

ProcessorAMD EPYC 7R13 Processor
Architecturex86_64 (x86_64)
vCPUs / Threads64 vCPUs
Physical Cores32
Clock Speed2.6 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score1,380,873
CoreMark / vCPU21,576.1 / core
FFmpeg Transcoding134 FPS
CoreMark per Dollar406,522 score / $
Cost per vCPU-hr$0.0531
Cost per GiB-hr$0.0133

Containers & Kubernetes

EKS Max Pods737 pods
Max ECS Tasks120 tasks
Max ENIs15
IPv4/v6 per ENI50
Total Addressable IPs750 total IPs
CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network Performance25 Gigabit
Baseline Bandwidth25 Gbps
Burst / Peak Bandwidth25 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationNVMe SSD (1880 GB)
Local NVMe Disk1880 GB
EBS Baseline Throughput2500 MB/s
EBS Max Throughput2500 MB/s
EBS Baseline IOPS80,000
EBS Max / Burst IOPS80,000
Dedicated EBS Throughput20000 Mbps

GPU & Hardware Acceleration

GPU ModelNVIDIA L4
Accelerator Count1x GPU(s)
Total GPU Memory24.0 GB
Memory ArchitectureGDDR / HBM
CUDA Compute Capabilityv8.9
Acceleration RuntimesCUDA, TensorRT, cuDNN, PyTorch, PyJAX

Platform & Architecture Details

Hypervisor / SystemAWS Nitro System (PCIe Offload)
Nitro EnclavesSupported (Isolated security enclaves)
Normalization Factor4.220675944
Generation StatusCurrent Generation (Recommended)
Date Introduced2024-04-04

Regional Pricing Matrix

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$3.3968/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$5.7739/ hr
South America (Sao Paulo) (sa-east-1)
Global Fleet Average
$4.1529/ hr
Across all active regions
Regional Coverage
20regions
Available worldwide
Linux — Available in all 20 regions
Region NameRegion CodeOn-Demand Price
Asia Pacific (Hyderabad)
ap-south-2$4.0789
Asia Pacific (Malaysia)
ap-southeast-5$4.2789
Asia Pacific (Mumbai)
ap-south-1$4.0789
Asia Pacific (Seoul)
ap-northeast-2$4.1768
Asia Pacific (Sydney)
ap-southeast-2$4.4165
Asia Pacific (Tokyo)
ap-northeast-1$4.9264
AWS GovCloud (US-East)
us-gov-east-1$4.2815
AWS GovCloud (US-West)
us-gov-west-1$4.2815
Canada (Central)
ca-central-1$3.7716
EU (Frankfurt)
eu-central-1$4.2477
EU (London)
eu-west-2$4.3118
EU (Paris)
eu-west-3$4.3118
EU (Stockholm)
eu-north-1$3.6028
Europe (Spain)
eu-south-2$3.5791
Europe (Zurich)
eu-central-2$4.5794
Middle East (UAE)
me-central-1$4.1710
South America (Sao Paulo)Highest
sa-east-1$5.7739
US East (N. Virginia)Lowest
us-east-1$3.3968
US East (Ohio)Lowest
us-east-2$3.3968
US West (Oregon)Lowest
us-west-2$3.3968